Full Text:
<95>
CLC number:
On-line Access: 2025-01-25
Received: 2024-07-02
Revision Accepted: 2024-12-09
Crosschecked: 0000-00-00
Cited: 0
Clicked: 122
A subspace-based few-shot intrusion detection system for the Internet of Things
| |||||||||||||
Zhihui LI1,2, Congyuan XU2, Kun DENG2, Chunyuan LIU2. A subspace-based few-shot intrusion detection system for the Internet of Things[J]. Frontiers of Information Technology & Electronic Engineering, 1998, -1(-1): .
@article{title="A subspace-based few-shot intrusion detection system for the Internet of Things",
author="Zhihui LI1,2, Congyuan XU2, Kun DENG2, Chunyuan LIU2",
journal="Frontiers of Information Technology & Electronic Engineering",
volume="-1",
number="-1",
pages="",
year="1998",
publisher="Zhejiang University Press & Springer",
doi="10.1631/FITEE.2400556"
}
%0 Journal Article
%T A subspace-based few-shot intrusion detection system for the Internet of Things
%A Zhihui LI1
%A 2
%A Congyuan XU2
%A Kun DENG2
%A Chunyuan LIU2
%J Journal of Zhejiang University SCIENCE C
%V -1
%N -1
%P
%@ 2095-9184
%D 1998
%I Zhejiang University Press & Springer
%DOI 10.1631/FITEE.2400556
TY - JOUR
T1 - A subspace-based few-shot intrusion detection system for the Internet of Things
A1 - Zhihui LI1
A1 - 2
A1 - Congyuan XU2
A1 - Kun DENG2
A1 - Chunyuan LIU2
J0 - Journal of Zhejiang University Science C
VL - -1
IS - -1
SP -
EP -
%@ 2095-9184
Y1 - 1998
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/FITEE.2400556
Abstract: Deep learning-based intrusion detection systems rely on numerous training samples to achieve satisfactory detection rates. However, in real-world internet of Things (IoT) environments, the diversity of IoT devices and the subsequent fragmentation of attack types result in a limited number of training samples, which urgently requires researchers to develop few-shot intrusion detection systems. In this study, we propose a subspace-based approach for few-shot IoT intrusion detection systems to cope with the dilemma of insufficient learnable samples. The method is based on the principle of classifying metrics to identify network traffic. After feature extraction of samples, a subspace is constructed for each category. Next, the distance between the query samples and the subspace is calculated by the metric module, thus detecting malicious samples. Subsequently, based on the CICIOT2023 dataset we constructed a few-shot IoT intrusion-detection dataset and evaluated the proposed method. For the detection of unknown categories, the detection accuracies were 93.52% in the 5-way 1-shot setting, 92.99% in the 5-way 5-shot setting and 93.65% in the 5-way 10-shot setting.
Open peer comments: Debate/Discuss/Question/Opinion
<1>